On-street Parking Occupancy Detection
Collecting parking demand data is complex, especially for on-street spaces in urban cities. Traditional parking sensors like magnetic pucks and cameras are costly, infrastructure-invasive, and hard to scale. Moreover, magnetic pucks encounter lower accuracy in adverse operating conditions, and cameras are constrained by limited mounting locations on public poles. Neither can be scaled properly to an entire city because each puck captures only one space and each camera a handful. Manual surveys are a possible alternative, but they cannot be done frequently as they highly rely on human resources.
We developed an alternative approach to parking demand data collection that leverages dashcams on moving bikes. We begin by geofencing existing on-street parking zones based on the Toronto Parking Authority’s Green-P zones. We then use vision AI models to detect vehicle presence when a bike crosses the designated fence and enters the parking zone. Every time a parking zone is visited, the occupancy ground truth is revealed. Therefore, the occupancy prediction accuracy improves with the number of visits per parking zone. The data is subsequently analyzed and visualized on a GIS-based tool to enhance data-driven parking policy decision-making, such as pricing and enforcement.
Camera-based Parking Lot Occupancy Detection
Finding convenient parking is difficult in cities where occupancy information is unavailable. We use YOLOv8, a computer vision object detection model provided by Ultralytics, to detect the occupancy status of individual parking spaces in a lot. We display parking spaces as polygons and use green and red to represent empty and occupied spaces, respectively. The real-time detected occupancy of the lots is then aggregated and displayed on a web app accessible to all.